Using Machine Learning Algorithms for Breast Cancer Risk Prediction and Diagnosis

Machine learning (ML) based forecasting mechanisms have proved their significance to anticipate in perioperative outcomes to improve the decision making on the future course of actions. The ML models have long been used in many application domains which needed the identification and prioritization of adverse factors for a threat. Several prediction methods are being popularly used to handle forecasting problems. This study demonstrates the capability of ML models to forecast the number of upcoming patients affected by COVID-19 which is presently considered as a potential threat to mankind. In particular, four standard forecasting models, such as linear regression (LR), least absolute shrinkage and selection operator (LASSO), support vector machine (SVM), and exponential smoothing (ES) have been used in this study to forecast the threatening factors of COVID-19. Three types of predictions are made by each of the models, such as the number of newly infected cases, the number of deaths, and the number of recoveries in the next 10 days. The results produced by the study proves it a promising mechanism to use these methods for the current scenario of the COVID-19 pandemic. The results prove that the ES performs best among all the used models followed by LR and LASSO which performs well in forecasting the new confirmed cases, death rate as well as recovery rate, while SVM performs poorly in all the prediction scenarios given the available dataset.

/pdf/covid-19-future-forecasting-using-supervised-machine-3nat3im5cb.pdf

COVID-19 Future Forecasting Using Supervised Machine Learning Models

Federated learning has been a hot research topic in enabling the collaborative training of machine learning models among different organizations under the privacy restrictions. As researchers try to support more machine learning models with different privacy-preserving approaches, there is a requirement in developing systems and infrastructures to ease the development of various federated learning algorithms. Similar to deep learning systems such as PyTorch and TensorFlow that boost the development of deep learning, federated learning systems (FLSs) are equivalently important, and face challenges from various aspects such as effectiveness, efficiency, and privacy. In this survey, we conduct a comprehensive review on federated learning systems. To achieve smooth flow and guide future research, we introduce the definition of federated learning systems and analyze the system components. Moreover, we provide a thorough categorization for federated learning systems according to six different aspects, including data distribution, machine learning model, privacy mechanism, communication architecture, scale of federation and motivation of federation. The categorization can help the design of federated learning systems as shown in our case studies. By systematically summarizing the existing federated learning systems, we present the design factors, case studies, and future research opportunities.

A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection

This research study explores the Global Positioning System (GPS), its history, and the process of discovery needed to create the most accurate GPS possible, as well as the contemporary applications of GPS technology. Starting with the first satellite in space, GPS has been a work in progress. Originally pursued by the military for improvements to military tactics, GPS has become integrated into the everyday lives of millions of people around the world. How GPS determines location is a dichotomy, with simplistic theory and complex application. Many factors go into GPS to provide a consistent, accurate location. The orbital planes the satellites are placed in provide 24/7 coverage globally, the L-band frequencies used were chosen specifically for the characteristics they possess, and the multiple atomic clocks installed on each satellite provide incredible accuracy down to the nanoseconds, which is quintessential in GPS accuracy. The applications in GPS are far reaching and more applications are continually being discovered. With as far as GPS technology has progressed, there are still several factors that degrade the signal and are a challenge to overcome. Many of these challenges can be corrected efficiently, however, others, such as scintillation and total electron content variability in the ionosphere, create major hurdles to overcome. Luckily, there are many programs that aid in the correction process of these hurdles. The History of GPS According to R. Saunders’ article ​A Short History of GPS Development,​ The Global Positioning System (GPS) has a long history of trial and error and refinement and improvement. It’s purpose has shifted from being a military strategic asset to commonplace among the general public with its use in traveling, farming, and even banking. The beginning of GPS, introduced with a simple idea, can be traced back to the Soviet Union in the late 1950’s. In 1957, the Soviet Union made history with successfully launching the first satellite in space. To track the satellite Sputnik, Physicists and Scientists at John Hopkins University’s Applied Physics Laboratory listened to the beeps Sputnik’s signals produced. They noticed that the beeps had a Doppler Effect or Doppler Shift as the satellite passed by. Much like the sound a siren makes as a fire truck approaches, then as it passes, the sound of the siren seems different. The change in timing between the beeps let the scientist know Sputnik’s location. This led to the idea of reversing that process, to give a location on the Earth. Using radio frequencies to determine location in a two dimensional plane had been around since WWII, but using satellites would push this technology into the three dimensional realm. The United States Navy, Army, and Air Force all began developing their own GPS satellites in the 1960’s, but this was no small task. In the early 1960’s, the Navy launched its first Transit Satellite. The failure of this satellite, however, was due to

/pdf/the-global-positioning-system-30ag469ov3.pdf

The Global Positioning System

Breast cancer is associated with the highest morbidity rates for cancer diagnoses in the world and has become a major public health issue. Early diagnosis can increase the chance of successful treatment and survival. However, it is a very challenging and time-consuming task that relies on the experience of pathologists. The automatic diagnosis of breast cancer by analyzing histopathological images plays a significant role for patients and their prognosis. However, traditional feature extraction methods can only extract some low-level features of images, and prior knowledge is necessary to select useful features, which can be greatly affected by humans. Deep learning techniques can extract high-level abstract features from images automatically. Therefore, we introduce it to analyze histopathological images of breast cancer via supervised and unsupervised deep convolutional neural networks. First, we adapted Inception_V3 and Inception_ResNet_V2 architectures to the binary and multi-class issues of breast cancer histopathological image classification by utilizing transfer learning techniques. Then, to overcome the influence from the imbalanced histopathological images in subclasses, we balanced the subclasses with Ductal Carcinoma as the baseline by turning images up and down, right and left, and rotating them counterclockwise by 90 and 180 degrees. Our experimental results of the supervised histopathological image classification of breast cancer and the comparison to the results from other studies demonstrate that Inception_V3 and Inception_ResNet_V2 based histopathological image classification of breast cancer is superior to the existing methods. Furthermore, these findings show that Inception_ResNet_V2 network is the best deep learning architecture so far for diagnosing breast cancers by analyzing histopathological images. Therefore, we used Inception_ResNet_V2 to extract features from breast cancer histopathological images to perform unsupervised analysis of the images. We also constructed a new autoencoder network to transform the features extracted by Inception_ResNet_V2 to a low dimensional space to do clustering analysis of the images. The experimental results demonstrate that using our proposed autoencoder network results in better clustering results than those based on features extracted only by Inception_ResNet_V2 network. All of our experimental results demonstrate that Inception_ResNet_V2 network based deep transfer learning provides a new means of performing analysis of histopathological images of breast cancer.

/pdf/deep-learning-based-analysis-of-histopathological-images-of-3m0zssgdak.pdf

Deep Learning Based Analysis of Histopathological Images of Breast Cancer.

Mobile phones, sensors, patients, hospitals, researchers, providers and organizations are nowadays, generating huge amounts of healthcare data. The real challenge in healthcare systems is how to find, collect, analyze and manage information to make people's lives healthier and easier, by contributing not only to understand new diseases and therapies but also to predict outcomes at earlier stages and make real-time decisions. In this paper, we explain the potential benefits of big data to healthcare and explore how it improves treatment and empowers patients, providers and researchers. We also describe the ability of reality mining in collecting large amounts of data to understand people's habits, detect and predict outcomes, and illustrate the benefits of big data analytics through five effective new pathways that could be adopted to promote patients' health, enhance medicine, reduce cost and improve healthcare value and quality. We cover some big data solutions in healthcare and we shed light on implementations, such as Electronic Healthcare Record (HER) and Electronic Healthcare Predictive Analytics (e-HPA) in US hospitals. Furthermore, we complete the picture by highlighting some challenges that big data analytics faces in healthcare.

Big data in healthcare: Challenges and opportunities

Mobile phone and sensors have become very useful to understand and analyze human lifestyle because of the huge amount of data they can collect every second. This triggered the idea of combining benefits and advantages of reality mining, machine learning and big data predictive analytics tools, applied to smartphones/sensors real time. The main goal of our study is to build a system that interacts with mobile phones and wearable healthcare sensors to predict patterns. Wearable healthcare sensors (heart rate sensor, temperature sensor and activity sensor) and mobile phone are used for gathering real time data. All sensors are managed using IoT systems; we used Arduino for collecting data from health sensors and Raspberry Pi 3 for programming and processing. Kmeans clustering algorithm is used for patterns prediction and predicted clusters (partitions) are transmitted to the user in his front-end interface in the mobile application. Real world data and clustering validation statistics (Elbow method and Silhouette method) are used to validate the proposed system and assess its performance and effectiveness. All data management and processing tasks are conducted over Apache Spark Databricks. This system relies on real time gathered data and can be applied to any prediction case making use of sensors and mobile generated data. As a proof of concept, we worked on predicting miscarriages to help pregnant women make quick decisions in case of miscarriage or probable miscarriage by creating a real time system prediction of miscarriage using wearable healthcare sensors, mobile tools, data mining algorithms and big data technologies. 9 risk factors contribute vastly in prediction, the Elbow method asserts that the optimal number of cluster is 2 and we achieve a higher value (0, 95) of Silhouette width that validates the good matching between clusters and observations. K-means algorithm gives good results in clustering the data.

/pdf/reality-mining-and-predictive-analytics-for-building-smart-t9kskzfrh6.pdf

Hiba Asri

Papers

Using Machine Learning Algorithms for Breast Cancer Risk Prediction and Diagnosis

Big data in healthcare: Challenges and opportunities

Reality mining and predictive analytics for building smart applications

Real-time Miscarriage Prediction with SPARK

Comprehensive miscarriage dataset for an early miscarriage prediction.